R Notebook

This is an R Markdown Notebook. When you execute code within the notebook, the results appear beneath the code.

Try executing this chunk by clicking the Run button within the chunk or by placing your cursor inside it and pressing Ctrl+Shift+Enter.

Add a new chunk by clicking the Insert Chunk button on the toolbar or by pressing Ctrl+Alt+I.

When you save the notebook, an HTML file containing the code and output will be saved alongside it (click the Preview button or press Ctrl+Shift+K to preview the HTML file).

The preview shows you a rendered HTML copy of the contents of the editor. Consequently, unlike Knit, Preview does not run any R code chunks. Instead, the output of the chunk when it was last run in the editor is displayed.

library(tidyverse)
# install for visualizations 
library(ggplot2)
# install to combine date and time
library(lubridate)

wego <- read_csv("../data/Route 50 Timepoint and Headway Data, 1-1-2023 through 5-12-2025.csv")

wego

# Create new date time column
wego$DATE_TIME <- ymd(wego$DATE) + hms(wego$SCHEDULED_TIME)

# Examine Data
wego

# Filter February TSP values
feb3_10_tsp <- wego |> 
  filter(between(DATE_TIME, 
                 as.Date("2025-02-03 12:00:00"), 
                 as.Date("2025-02-10 12:00:00")))

# Filter Feb-Apr TSP with busses only 2 minutes late or more
feb10_apr28_tsp <- wego |> 
  filter(between(DATE_TIME, 
                 as.Date("2025-02-10 12:00:00"), 
                 as.Date("2025-04-28 12:00:00"))) |> 
  filter(ADHERENCE <= -2)

# Filter May TSP values
may5_12_tsp <- wego |> 
  filter(between(DATE_TIME, 
                 as.Date("2025-05-05 12:00:00"), 
                 as.Date("2025-05-12 12:00:00")))

  

# Add day of week column
wego <- wego |>
  mutate(
    DATE_TIME = as.POSIXct(DATE_TIME),
    DAY_OF_WEEK = wday(DATE_TIME, 
                       label = TRUE, 
                       abbr = FALSE))

wego

NA

# Combine tsp variables into one 
tsp_rows <- bind_rows(
  feb3_10_tsp,
  feb10_apr28_tsp,
  may5_12_tsp
) |> 
  select('ADHERENCE_ID', 'DATE_TIME') |> 
  distinct() |> 
  mutate(tsp = 1)  # Add tsp indicator column for each distinct adherence id

wego <- wego |> 
  left_join(
    tsp_rows,
    by = c('ADHERENCE_ID', 'DATE_TIME')
  ) |> 
  mutate(tsp = coalesce(tsp, 0))

wego |> view()

wego <- wego |>  mutate(
  tsp_indicator = if_else(
    between(DATE_TIME, 
            as.Date("2025-02-03 12:00:00"), 
            as.Date("2025-02-10 12:00:00")) |
    (between(DATE_TIME, 
            as.Date("2025-02-10 12:00:00"), 
            as.Date("2025-04-28 12:00:00")) &
       ADHERENCE <= -2) |
    between(DATE_TIME, 
            as.Date("2025-05-05 12:00:00"), 
            as.Date("2025-05-12 12:00:00")), 1, 0)
    
  )

wego

NA

wego <- wego |> mutate(
  HOUR = hms(SCHEDULED_TIME) |> 
    hour()
  )

wego <- wego |>
  mutate(
    time_of_day = case_when(
      between(HOUR, 4, 5) ~ "early_morning",
      between(HOUR, 6, 8) ~ "morning_peak",
      between(HOUR, 9, 14) ~ "midday",
      between(HOUR, 15, 17) ~ "pm_peak",
      between(HOUR, 18, 20) ~ "evening",
      between(HOUR, 21, 23) ~ "late_night",
      between(HOUR, 0, 3) ~ "late_night",
      .default = "other"
    )
  )

wego

NA

tod_table = table(wego$time_of_day)
pt_tod_table <- prop.table(tod_table)

pt_tod_table

early_morning       evening    late_night        midday  morning_peak         other       pm_peak 
   0.03272224    0.12055936    0.09740419    0.36547452    0.16413139    0.03097748    0.18873082 

tod_table

early_morning       evening    late_night        midday  morning_peak         other       pm_peak 
        20255         74626         60293        226228        101597         19175        116824 

barplot(table(wego$time_of_day), main = "Time of day distribution")

table_tod <- pt_tod_table 
# Create a color vector
color <- rainbow(nrow(table_tod))
# Set the rotation for x-axis labels to 45 degrees
par(las=2)
# Create the vertically stacked bar plot
bp <- barplot(table_tod, main = "Time of day distribution", col = color)
# Add the legend
legend("topright", legend = rownames(table_tod),cex = 0.75, fill = color)

# Add x-axis labels with a 45 degree angle
# axis(1, at=bp, labels=colnames(table_tod), las=2, cex.axis=2)

late_tod <- table(wego$time_of_day, wego$ADJUSTED_LATE_COUNT)
# Create a color vector
color <- rainbow(nrow(late_tod))
# Set the rotation for x-axis labels to 45 degrees
par(las=2)
# Create the vertically stacked bar plot
bp <- barplot(late_tod, main = "Late bus dist", col = color)
# Add the legend
legend("topright", legend = rownames(late_tod),cex = 0.9, fill = color)

# Add x-axis labels with a 45 degree angle
axis(1, at=bp, labels=colnames(late_tod), las=2, cex.axis=1)

count_tod <- wego |>
  count(time_of_day)

count_tod

unique(wego$ADJUSTED_LATE_COUNT)

[1] 0 1

wego

# count_tod <- wego |>
#   count(time_of_day)
# # value <- count_tod$n
# value = count_tod
#   # table(wego$time_of_day)
# condition <- tod <- c("early_morning", "morning_peak", "midday", "pm_peak", "evening", "late_night", "late_night", "other") #wego$time_of_day
# specie <- wego$ADJUSTED_LATE_COUNT
# 
# ggplot(wego, aes(fill=condition, y=value, x=specie)) + 
#     geom_bar(position="fill", stat="identity")

wego_tod_count_late <- wego |> 
  group_by(time_of_day, ADJUSTED_LATE_COUNT) |> 
  summarize(n = n())


wego_tod_count_late

ggplot(wego_tod_count_late, aes(fill=time_of_day, y=n, x=factor(ADJUSTED_LATE_COUNT))) + 
  geom_bar(position="fill", stat="identity")+ 
  xlab("Ontime (0) and Late (1) Buses") +
  ylab("Proportion of Buses") +
  ggtitle("Proportion of Late and Ontime Buses")